On Feature Decorrelation in Self-Supervised Learning

Tianyu Hua, Wenxiao Wang, Zihui Xue, Sucheng Ren, Yue Wang, Hang Zhao; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 9598-9608


In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations. A potential issue of this idea is the existence of completely collapsed solutions (i.e., constant features), which are typically avoided implicitly by carefully chosen implementation details. In this work, we study a relatively concise framework containing the most common components from recent approaches. We verify the existence of complete collapse and discover another reachable collapse pattern that is usually overlooked, namely dimensional collapse. We connect dimensional collapse with strong correlations between axes and consider such connection as a strong motivation for feature decorrelation (i.e., standardizing the covariance matrix). The gains from feature decorrelation are verified empirically to highlight the importance and the potential of this insight.

Related Material

[pdf] [arXiv]
@InProceedings{Hua_2021_ICCV, author = {Hua, Tianyu and Wang, Wenxiao and Xue, Zihui and Ren, Sucheng and Wang, Yue and Zhao, Hang}, title = {On Feature Decorrelation in Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {9598-9608} }